© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 71239
    Prev
    Next
    INDEX
    Explanations

    Childhood death/survival

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -wall
    -0.08
    ോള
    -0.08
    walls
    -0.08
     Inspiration
    -0.08
     JFrame
    -0.08
     décou
    -0.08
    imat
    -0.08
     Sega
    -0.08
     pétrole
    -0.08
     Presiden
    -0.08
    POSITIVE LOGITS
     mortality
    0.11
     illnesses
    0.09
     abort
    0.09
     ایس
    0.09
     મૃત્યુ
    0.09
     मृत्यु
    0.09
     infelizmente
    0.09
     মৃত্য
    0.09
     infant
    0.09
     मृत
    0.09
    Activations Density 0.012%

    No Known Activations